INDEX

Explanations

phrases related to the name "Mardi Gras"

oai_token-act-pair · gpt-3.5-turbo

the name "Lombardi" and related references in the context of various discussions or events

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

mits

-0.93

piring

-0.85

esty

-0.85

pir

-0.83

ted

-0.82

lisher

-0.80

locked

-0.80

manship

-0.77

orate

-0.77

locks

-0.76

POSITIVE LOGITS

ardi

0.96

osa

0.88

 Trophy

0.75

cki

0.71

dinand

0.69

ectomy

0.68

otti

0.67

asso

0.66

Äĩ

0.65

 Typhoon

0.64

Activations Density 0.018%

phrases related to the name "Mardi Gras"

the name "Lombardi" and related references in the context of various discussions or events

No Comments

No Known Activations